zilliztech/claude-context

4.7

Adjusted Score

4.7

Raw Score

100%

Time Factor

2026-07-14

Last Push

12.1K

Stars

TypeScript

Language

34.0K

Lines of Code

136

Files

115

Pattern Hits

2026-07-14

Scan Date

0.01

HC Hit Rate

What These Metrics Mean

Adjusted Score: Primary synthetic code indicator. Raw score normalised per 1,000 lines of code and multiplied by the temporal discount factor. This is the definitive comparative metric — use it to rank repositories by AI authorship density.
Raw Score: The unmodified sum of all severity-weighted, context-multiplied pattern match scores before temporal discounting. Reflects the absolute signal strength independent of when the repository was last active.
Time Factor: The temporal discount multiplier (0–100%) applied to the raw score. Repositories last updated before ChatGPT's launch (Nov 2022) receive a 5% factor. Full signal is only assigned to repositories active in the post-adoption era (Jan 2024+).
Pattern Hits: Total count of individual pattern matches across all files and categories. A high hit count with a low score may indicate a very large codebase with isolated AI snippets; a low count with a high score indicates dense, concentrated AI signatures.
HC Hit Rate: High+Critical pattern hits per file, averaged across the repository. This orthogonal signal catches repositories where a few files are densely packed with high-severity AI tells — a strong indicator even when the normalised score appears moderate due to codebase size.
Lines of Code / Files: Total lines and files analysed. The scanner examines 94 file extensions. These denominators are used to normalise the score, enabling fair comparison between repositories of vastly different sizes.

Score History

This chart maps the temporal evolution of the adjusted synthetic code score across successive scan runs. An upward trajectory indicates ongoing incorporation of AI-generated code or expanding LLM-assisted scaffolding; a stable or declining trajectory may reflect active human refactoring, code removal, or the adoption of stricter authorship policies. The dashed secondary line (right axis) independently tracks total raw pattern hit count, which can diverge from the normalised score when codebase size changes significantly between scans.

Severity Breakdown

Classifies detected patterns by their diagnostic confidence and structural impact. CRITICAL patterns (coefficient 10) represent definitive synthetic signatures — hallucinated imports, explicit LLM attribution metadata — virtually never produced by human authors. HIGH (5) indicates strong structural tells such as cross-file repetition or cross-linguistic idioms. MEDIUM (2) covers recognisable conversational padding and AI-specific vocabulary. LOW (1) captures subtle indicators like tautological comments and generic boilerplate that require density to carry independent signal.

CRITICAL 0HIGH 1MEDIUM 12LOW 102

Directory Score Breakdown

This horizontal bar chart decomposes the repository's raw synthetic code score by top-level directory, allowing you to pinpoint precisely which modules or components carry the highest AI authorship density. Directories with disproportionately high scores relative to their size warrant targeted manual review: concentrated AI signatures often trace back to mass-generated configuration layers, auto-ported test suites, LLM-scaffolded boilerplate classes, or entire subsystems authored under heavy copilot assistance. Use this view to prioritise your human code-review effort.

Pattern Findings

The scanner identified 115 distinct pattern matches across 14 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a statistically significant AI authorship indicator. Expand any category row to inspect the individual file paths, line numbers, code snippets, and the lexical context (CODE, COMMENT, or STRING) in which each match was detected.

Reading the findings table: The Severity column indicates the diagnostic confidence level (CRITICAL / HIGH / MEDIUM / LOW). The Context column identifies whether the match occurred inside executable code, an inline comment, or a string literal — comment-context matches receive a ×1.5 weight because LLMs systematically over-annotate. The ⚡ bolt icon marks clustered matches: three or more patterns within a 10-line window, each receiving an additional ×1.5 density multiplier as dense clusters constitute far stronger evidence of synthetic authorship than isolated hits.

Structural Annotation Overuse19 hits · 33 pts

Severity	File	Line	Snippet	Context
LOW	docs/troubleshooting/troubleshooting-guide.md	10	### Step 1: Check Indexing Status First	COMMENT
LOW	docs/troubleshooting/troubleshooting-guide.md	22	### Step 2: Get Debug Logs	COMMENT
LOW	docs/troubleshooting/troubleshooting-guide.md	44	### Step 3: Reconnect MCP Server After Configuration Changes	COMMENT
LOW	docs/troubleshooting/troubleshooting-guide.md	64	### Step 4: Search Documentation and Community	COMMENT
LOW	docs/troubleshooting/troubleshooting-guide.md	79	### Step 5: Report the Issue	COMMENT
LOW	docs/troubleshooting/troubleshooting-guide.md	83	### Step 6: After Version Updates	COMMENT
LOW	docs/troubleshooting/troubleshooting-guide.md	96	### Step 1: Get Debug Logs	COMMENT
LOW	docs/troubleshooting/troubleshooting-guide.md	107	### Step 2: Search Documentation and Community	COMMENT
LOW	docs/troubleshooting/troubleshooting-guide.md	122	### Step 3: Report the Issue	COMMENT
LOW	docs/troubleshooting/troubleshooting-guide.md	126	### Step 4: After Version Updates	COMMENT
LOW	docs/getting-started/quick-start.md	7	### Step 1: Get API Keys	COMMENT
LOW	docs/getting-started/quick-start.md	15	### Step 2: Configure Claude Code	COMMENT
LOW	docs/getting-started/quick-start.md	29	### Step 3: Start Using Claude Context	COMMENT
LOW⚡	packages/core/src/vectordb/milvus-restful-vectordb.ts	256	// Step 1: Create collection with schema	COMMENT
LOW⚡	packages/core/src/vectordb/milvus-restful-vectordb.ts	259	// Step 2: Create index for vector field (separate API call)	COMMENT
LOW⚡	packages/core/src/vectordb/milvus-restful-vectordb.ts	262	// Step 3: Load collection to memory for searching	COMMENT
LOW⚡	packages/core/src/vectordb/milvus-restful-vectordb.ts	606	// Step 1: Create collection with schema and functions	COMMENT
LOW⚡	packages/core/src/vectordb/milvus-restful-vectordb.ts	609	// Step 2: Create indexes for both vector fields	COMMENT
LOW⚡	packages/core/src/vectordb/milvus-restful-vectordb.ts	612	// Step 3: Load collection to memory for searching	COMMENT

Self-Referential Comments7 hits · 19 pts

Severity	File	Line	Snippet	Context
MEDIUM	evaluation/analyze_and_plot_mcp_efficiency.py	367	# Create the efficiency chart	COMMENT
MEDIUM	evaluation/generate_subset_json.py	50	# Create the JSON structure that _prepare_instances expects	COMMENT
MEDIUM	evaluation/retrieval/custom.py	126	# Create the appropriate context manager based on which sessions we need	COMMENT
MEDIUM	evaluation/retrieval/base.py	55	# Create a simple dict that mimics HuggingFace dataset structure	STRING
MEDIUM	evaluation/servers/edit_server.py	10	# Create the MCP server	COMMENT
MEDIUM	evaluation/servers/read_server.py	15	# Create the MCP server	COMMENT
MEDIUM	evaluation/servers/grep_server.py	16	# Create the MCP server	COMMENT

Deep Nesting18 hits · 18 pts

Severity	File	Line	Context
LOW	python/test_endtoend.py	17	CODE
LOW	python/ts_executor.py	26	CODE
LOW	evaluation/analyze_and_plot_mcp_efficiency.py	54	CODE
LOW	evaluation/utils/format.py	6	CODE
LOW	evaluation/utils/format.py	25	CODE
LOW	evaluation/utils/format.py	108	CODE
LOW	evaluation/utils/format.py	262	CODE
LOW	evaluation/utils/format.py	349	CODE
LOW	evaluation/utils/file_management.py	13	CODE
LOW	evaluation/utils/llm_factory.py	7	CODE
LOW	evaluation/retrieval/custom.py	293	CODE
LOW	evaluation/retrieval/base.py	42	CODE
LOW	evaluation/retrieval/base.py	126	CODE
LOW	evaluation/servers/read_server.py	20	CODE
LOW	evaluation/servers/read_server.py	137	CODE
LOW	evaluation/servers/read_server.py	186	CODE
LOW	evaluation/servers/read_server.py	211	CODE
LOW	evaluation/servers/grep_server.py	36	CODE

Hyper-Verbose Identifiers18 hits · 18 pts

Severity	File	Line	Snippet	Context
LOW	python/test_endtoend.py	17	def run_context_endtoend_test():	CODE
LOW	packages/core/src/vectordb/milvus-restful-vectordb.ts	37	async function createCollectionWithLimitCheck(	CODE
LOW	packages/chrome-extension/src/background.ts	403	async function handleTestMilvusConnection(sendResponse: Function) {	CODE
LOW	packages/mcp/src/splitter.ts	9	export function resolveRequestSplitterType(splitterType: unknown): RequestSplitterType {	CODE
LOW	packages/mcp/src/config.ts	84	export function getDefaultModelForProvider(provider: string): string {	CODE
LOW	packages/mcp/src/config.ts	102	export function getEmbeddingModelForProvider(provider: string): string {	CODE
LOW	packages/mcp/src/config.ts	121	function getPositiveIntegerFromEnv(name: string): number \| undefined {	CODE
LOW	packages/mcp/src/sync.ts	41	function getBackgroundSyncIntervalMs(): number {	CODE
LOW	packages/vscode-extension/src/extension.ts	184	function reloadContextConfiguration() {	CODE
LOW	evaluation/utils/format.py	25	def extract_file_paths_from_edits(response, codebase_path):	CODE
LOW	evaluation/utils/format.py	77	def _normalize_to_relative_path(file_path, codebase_path):	CODE
LOW	evaluation/utils/format.py	94	def extract_oracle_files_from_patch(patch):	CODE
LOW	evaluation/utils/format.py	108	def extract_edit_calls_from_conversation_log(log_content: str):	CODE
LOW	evaluation/utils/format.py	177	def find_line_number_for_old_string(file_path: str, old_string: str):	CODE
LOW	evaluation/utils/format.py	349	def extract_conversation_summary(response):	CODE
LOW	evaluation/utils/format.py	443	def print_conversation_summary(response):	CODE
LOW	evaluation/retrieval/custom.py	183	async def _load_tools_from_sessions(self, sessions: Dict):	CODE
LOW	evaluation/retrieval/base.py	126	def _filter_existing_instances(	STRING

Excessive Try-Catch Wrapping17 hits · 17 pts

Severity	File	Line	Snippet	Context
MEDIUM	python/test_endtoend.py	94	print(f"Error: {result.get('error')}")	CODE
LOW	python/test_endtoend.py	99	except Exception as e:	CODE
LOW	python/ts_executor.py	122	except Exception as e:	CODE
LOW	python/ts_executor.py	302	except Exception as e:	STRING
MEDIUM	python/ts_executor.py	303	print(f"Error: {e}")	STRING
LOW	evaluation/analyze_and_plot_mcp_efficiency.py	102	except Exception as e:	CODE
LOW	evaluation/utils/format.py	191	except Exception:	CODE
LOW	evaluation/utils/file_management.py	95	except Exception as e:	CODE
LOW	evaluation/retrieval/custom.py	279	except Exception as e:	CODE
LOW	evaluation/retrieval/custom.py	318	except Exception as clear_error:	CODE
LOW	evaluation/retrieval/custom.py	381	except Exception as e:	CODE
LOW	evaluation/retrieval/custom.py	390	except Exception as e:	CODE
LOW	evaluation/retrieval/base.py	207	except Exception as e:	STRING
LOW	evaluation/servers/read_server.py	132	except Exception as e:	CODE
LOW	evaluation/servers/read_server.py	181	except Exception as e:	CODE
LOW	evaluation/servers/read_server.py	266	except Exception as e:	CODE
LOW	evaluation/servers/grep_server.py	211	except Exception as e:	CODE

Redundant / Tautological Comments13 hits · 16 pts

Severity	File	Line	Snippet	Context
LOW	python/test_endtoend.py	48	# Output results	COMMENT
LOW	evaluation/generate_subset_json.py	44	# Check if it matches our criteria	COMMENT
LOW	evaluation/utils/format.py	126	# Check if the line contains complete arguments	COMMENT
LOW	evaluation/retrieval/base.py	44	# Check if it's a JSON file	STRING
LOW	evaluation/retrieval/base.py	109	# Check if we've already processed enough instances	STRING
LOW	evaluation/retrieval/base.py	153	# Check if output directory exists and has subdirectories with result.json	STRING
LOW	evaluation/servers/read_server.py	42	# Check if file exists	COMMENT
LOW	evaluation/servers/read_server.py	46	# Check if it's actually a file	COMMENT
LOW	evaluation/servers/read_server.py	153	# Check if directory exists	COMMENT
LOW	evaluation/servers/read_server.py	157	# Check if it's actually a directory	COMMENT
LOW	evaluation/servers/read_server.py	203	# Check if directory exists	COMMENT
LOW	evaluation/servers/read_server.py	207	# Check if it's actually a directory	COMMENT
LOW	evaluation/servers/grep_server.py	57	# Check if we're in a git repository and try git grep first	COMMENT

Verbosity Indicators6 hits · 14 pts

Severity	File	Line	Snippet	Context
LOW⚡	packages/core/src/vectordb/milvus-restful-vectordb.ts	256	// Step 1: Create collection with schema	COMMENT
LOW⚡	packages/core/src/vectordb/milvus-restful-vectordb.ts	259	// Step 2: Create index for vector field (separate API call)	COMMENT
LOW⚡	packages/core/src/vectordb/milvus-restful-vectordb.ts	262	// Step 3: Load collection to memory for searching	COMMENT
LOW⚡	packages/core/src/vectordb/milvus-restful-vectordb.ts	606	// Step 1: Create collection with schema and functions	COMMENT
LOW⚡	packages/core/src/vectordb/milvus-restful-vectordb.ts	609	// Step 2: Create indexes for both vector fields	COMMENT
LOW⚡	packages/core/src/vectordb/milvus-restful-vectordb.ts	612	// Step 3: Load collection to memory for searching	COMMENT

Modern AI Meta-Vocabulary3 hits · 9 pts

Severity	File	Line	Snippet	Context
MEDIUM	packages/mcp/README.md	50	# Optional: Specify embedding model (default: text-embedding-3-small)	COMMENT
MEDIUM	packages/mcp/README.md	78	# Optional: Specify embedding model (default: voyage-code-3)	COMMENT
MEDIUM	packages/mcp/README.md	103	# Optional: Specify embedding model (default: gemini-embedding-001; supports gemini-embedding-2)	COMMENT

Unused Imports6 hits · 6 pts

Severity	File	Line	Context
LOW	python/ts_executor.py	11	CODE
LOW	evaluation/analyze_and_plot_mcp_efficiency.py	13	CODE
LOW	evaluation/run_evaluation.py	6	CODE
LOW	evaluation/utils/format.py	1	CODE
LOW	evaluation/retrieval/custom.py	14	CODE
LOW	evaluation/servers/edit_server.py	7	CODE

Magic Placeholder Names1 hit · 5 pts

Severity	File	Line	Snippet	Context
HIGH	packages/mcp/package.json	18	"start:with-env": "OPENAI_API_KEY=${OPENAI_API_KEY:your-api-key-here} MILVUS_ADDRESS=${MILVUS_ADDRESS:localhost:	CODE

Modern Structural Boilerplate4 hits · 4 pts

Severity	File	Line	Snippet	Context
LOW	evaluation/run_evaluation.py	11	logger = logging.getLogger(__name__)	CODE
LOW	evaluation/utils/file_management.py	10	logger = logging.getLogger(__name__)	CODE
LOW	evaluation/retrieval/custom.py	23	logger = logging.getLogger(__name__)	CODE
LOW	evaluation/retrieval/base.py	18	logger = logging.getLogger(__name__)	CODE

Overly Generic Function Names1 hit · 1 pts

Severity	File	Line	Snippet	Context
LOW	python/ts_executor.py	234	export async function processData(data: any[]): Promise<{ count: number; items: any[] }> {	CODE

Over-Commented Block1 hit · 1 pts

Severity	File	Line	Snippet	Context
LOW	packages/chrome-extension/src/vm-stub.js	1	// This file is intentionally left blank to act as a stub for the 'vm' module in the browser environment.	COMMENT

Example Usage Blocks1 hit · 0 pts

Severity	File	Line	Snippet	Context
LOW	python/ts_executor.py	220	# Usage example	STRING

Analysis Overview

What These Metrics Mean

Score History

Severity Breakdown

Directory Score Breakdown

Pattern Findings